Abstract
One of the fundamental requirements for visual surveillance with Visual Sensor Networks (VSN) is the correct association of camera's observations with the tracks of objects under tracking. In this paper, we model the data association in VSN as an inference problem on dynamic Bayesian networks (DBN) and investigate the key problems for efficient data association in case of missing detection. Firstly, to deal with the problem of missing detection, we introduce a set of random variables, namely routine variables, into the DBN model to describe the uncertainty in the path taken by the moving objects and propose the high-order spatio-temporal model based inference algorithm. Secondly, for the problem of computational intractability of exact inference, we derive two approximate inference algorithms by factorizing the belief state based on the marginal and conditional independence assumptions. Thirdly, we incorporate the inference algorithm into EM framework to make the algorithm suitable for the case when object appearance parameters are unknown. Simulation and experimental results demonstrate the effect of the proposed methods.
Highlights
Consisting of a large number of cameras with nonoverlapping field of view, Visual Senor Networks (VSNs) have been frequently used for surveillance of public locations such as airports, subway stations, busy streets, and public buildings
It is interesting to note that a similar problem arise, in the multitargets tracking (MTT) research, where the goal is to associate the several distinct track segments produced by the same target
In this paper we address the problem of data association in visual sensor networks
Summary
Consisting of a large number of cameras with nonoverlapping field of view, Visual Senor Networks (VSNs) have been frequently used for surveillance of public locations such as airports, subway stations, busy streets, and public buildings. In the region covered by the VSN there are several moving objects (persons, cars, etc.), presenting in one camera at a certain time and reappearing in another after a certain period. The visual information captured by VSN can be used for interpreting and understanding the activities of moving objects in the monitored region. One of the basic requirements for achieving these goals is to accurately associate the observations produced by the visual node with the track of each object of interest. It is interesting to note that a similar problem arise, in the multitargets tracking (MTT) research, where the goal is to associate the several distinct track segments produced by the same target. The target motion model used in multitargets tracking is not available in VSN, as large blind regions always exist between camera nodes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
